Brainscape's Knowledge GenomeTM

Browse over 1 million classes created by top students, professors, publishers, and experts.


See full index

CS401 - AI > Intro to AI > Flashcards

Intro to AI Flashcards

1
Q

AI assistant VS co-pilot AI assistant?

A

AI assistant: AI makes decisions
Co-pilot assistant: AI assists humans make informed decisions.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

What is a LLM?
List 5 tasks it can do.

A

A model capable of general purpose language generation and understanding.
1. Q&A
2. Summarization
3. Language understanding
4. Language correction
5. Named entity recognition

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

What is (human) intelligence?

A

The ability to perceive information
and retain it as knowledge
to be applied
towards adaptive behaviors
within an environment/ context.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

What is ANI?
What is AGI?

A

ANI : Artificial Narrow Intelligence –> Narrow/ limited AI
AGI : Artificial General Intelligence –> Strong/ human-like AI

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

What is the definition of AI?

A

The science and engineering of making intelligent machines, especially intelligent programs. (think and act like humans)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

List 14 main AI techniques

A
  1. Search, Local search, adversarial search
  2. Classical search
  3. Knowledge representation (Knowledge graphs)
  4. Automated Reasoning
  5. Probabilistic reasoning
  6. Bayesian networks
  7. Hierarchical planning
  8. ML
  9. DL
  10. Computer vision
  11. Natural Language Processing
  12. Generative models
  13. Speech/ signal processing
  14. Robotics
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

What is an “agent”?

A

Anything that can be viewed as
- perceiving its environment
- through sensors
- and acting upon that environment
- through actuators

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

Draw the agent-environment diagram

A

(draw)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

What is a “rational agent”?

A

An agent that selects actions that will maximize its performance measures.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

What are “performance measures” of an AI agent?
Give 3 examples

A

Objective criteria for the success of an agents’ behavior.
- Robot driver : safely, fast
- Medical diagnosis system : healthy patient, minimize cost, legal
- Harvest robot : safety, fast

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

Define the components of an agent program (3).
What does it do?

A
  1. P - Percepts : the perceptual inputs of an agent at any given time.
  2. P* - Percept sequence : the complete history of what the agent has perceived.
  3. Agent function : the mapping of any given percept sequence to an action.
    f : P* (P0, P1, … Pn) –> A
  • Agent functions are implemented by the agent program.
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

What are the 2 main components of an intelligent agent? Define them.

A
  1. Agent program : the implementation of the agents perception-action mapping.
  2. Architecture : a device that can execute the agent program.
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

What is the “Task Environment”?
List its components. (4) and explain

A

The 4 main components of an agent is collectively called the task environment.
1. Performance measure : which qualities is should have.
2. Environment : where it should act
3. Actuators : how it will perform the actions
4. Sensors : how it will perceive the environment

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

What is the “Turing Test”? Define and explain

A
  • An experiment to identify if a machine exhibited intelligence.
  • A human judge communicates with both human and machine. Both respond and try to act human. If the machine succeeds in seeming human to the judge it is considered intelligent.
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

What are the basic capabilities an AI system requires to pass the
A)Turing Test?
B)Total Turing Test?

A

A)
1. NLP
2. Knowledge representation
3. Automated reasoning
4. Machine learning
B)
1. Computer vision
2. Robotics

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

What are the 04 main approaches to build an AI system?
Why will each of them not work? (03)
Why will the one that does do?

A
  1. Thinking humanly - no - brain’s hardware is different to a computer program. (cognitive science)
  2. Thinking rationally - no - world via logic, doesn’t account for the uncertainty.
  3. Acting humanly - no - human behavior - humans don’t behave rationally.
  4. Acting rationally - possible - act in the most logical way possible.
17
Q

What are the 06 main types of Environments & agents?

A
  1. Fully vs Partially observable
  2. Single vs multi agent
  3. Deterministic vs stochastic
  4. Episodic vs sequential
  5. Static vs dynamic
  6. Discrete vs continuous
18
Q

What are the 05 main types of Agents, based on Agent Program?
Draw the agent-environment diagram for each

A
  1. Simple reflex agents
  2. Model based reflex agents
  3. Goal based agents
  4. Utility based agents
  5. Learning agents
    * draw
19
Q

What are the 04 major factors agents can improve using?

A
  1. component
  2. prior knowledge
  3. presentation
  4. feedback
20
Q

What are some important hyperparameters?

A
  1. no of hidden layers
  2. activation fn
  3. optimizer
  4. loss fn
  5. learning rate
  6. batch size
  7. epochs
21
Q

What is a sample?

A

A single row of data

22
Q

What is batch size?

A

The no of samples to work through before updating the internal model parameters.

23
Q

What is an epoch?

A

The no of times the learning algorithm will work through the entire training dataset.

24
Q

What is,
1) bias
2) variance

A

1) bias - errors due to inaccurate assumptions/ simplifications made by the model
2) variance - how much a models estimates from different training sets differ from each other.

25
Q

Define
1) underfitting
2) overfitting
of a model

A

1) model is too simple to represent relevant class characteristics - HB, LV
2) model is too complex - noise

CS401 - AI (3 decks)

Brainscape helps you reach your goals faster, through stronger study habits.
© 2024 Bold Learning Solutions. Terms and Conditions